CN111522448B

CN111522448B - Method, device and equipment for providing input candidate items

Info

Publication number: CN111522448B
Application number: CN201910107652.8A
Authority: CN
Inventors: 余天照
Original assignee: Beijing Sogou Technology Development Co Ltd
Current assignee: Beijing Sogou Technology Development Co Ltd
Priority date: 2019-02-02
Filing date: 2019-02-02
Publication date: 2024-04-30
Anticipated expiration: 2039-02-02
Also published as: CN111522448A

Abstract

The invention discloses a method, a device and equipment for inputting candidate items, comprising the following steps: the method comprises the steps that a server side obtains a first conversion result obtained by a client side aiming at a character string input by a user, and analyzes the following content according to the input content of the user, wherein the input content at least comprises the first conversion result; and merging the first conversion result and the following content to obtain merged content, and sending the merged content to the client, wherein the merged content is used as a server-side input candidate item on the client. The server side sends the combined content obtained based on the character string input by the user to the client side, so that in the input process of the user, the server side provides different input candidate items for the user from the client side, enriches the input candidate items obtained by the user, saves the input cost of the next step of the user, and improves the input efficiency of the user.

Description

Method, device and equipment for providing input candidate items

Technical Field

The present invention relates to the field of input methods, and in particular, to a method, an apparatus, and a device for providing input candidates.

Background

For a string entered by a user, the input method system may convert the string and provide the conversion result as an input candidate for selection by the user. For example, the user enters the string "anjian", and the input method system may provide the conversion results of "key", "security", "case", etc., as input candidates to the user. Typically, the input method system converts a character string using a word stock local to the client to obtain input candidates. But word libraries local to the client often cannot provide longer and up-to-date terms due to limitations in memory space, processing power, etc. on the client. In order to enable the input method system to provide these terms as input candidates, the input method system is also provided with a word stock on the server side. Thus, for the character string input by the user, the input method system not only can use the word stock of the local client side to convert the character string to obtain the input candidate item, but also can use the word stock of the server side to convert the character string to obtain the input candidate item, so that the user can obtain richer input candidate word items, and the user input is simpler and more convenient.

However, in many cases, for the character string input by the user, the conversion result of the character string by using the word stock at the server side and the conversion result of the character string by using the local word stock at the client side are the same, and the user cannot obtain different input candidates from the client side and the server side, which makes the input candidates obtained by the user not abundant enough, and thus may make the input operation of the user more complicated.

Disclosure of Invention

The invention aims to provide a method, a device and equipment for providing input candidates, so that a server side can provide different input candidates for a user from a client side, the input candidates obtained by the user are richer, and the input operation of the user is simpler and more convenient.

In order to solve the above-mentioned technical problem, an embodiment of the present invention provides a method for providing input candidates, where the method is applied to a server, and includes:

acquiring a first conversion result of a character string input by a user on a client;

analyzing the context of the entered content according to the entered content, the entered content including at least the first conversion result;

Combining the first conversion result with the context content to form combined content;

Sending the combined content to the client;

The merged content is used as a server-side input candidate item on the client side.

In some possible implementations, the entered content further includes an context that has been entered on the client prior to the string entry.

In some possible implementations, the analyzing the context of the entered content from the entered content includes:

Acquiring the input content as a current context;

determining a context entry for the current context;

if the context probability of the current context and the context entry is greater than a probability threshold, re-using the content formed by the current context and the context entry as the current context, and returning to execute the context entry for determining the current context;

if the context probability of the current context and the context entry is not greater than a probability threshold, determining the part of the current context except the input content as the context content;

Wherein the context probability represents a likelihood that the current context and the context entry are entered as a context by a user.

In some possible implementations, the first conversion result is a conversion result obtained by converting the character string by using a word stock of the server side.

In some possible embodiments, the method further comprises:

sending the first conversion result to the client;

If the first conversion result meets a preset condition, the combined content is used as the server side input candidate item on the client side; and if the first conversion result does not meet the preset condition, the first conversion result is used as the server side input candidate item on the client side.

In some possible implementations, the analyzing the context of the inputted content according to the inputted content is specifically: if the first conversion result meets a preset condition, analyzing the context content of the input content according to the input content;

the sending the first conversion result to the client specifically includes: and if the first conversion result does not meet the preset condition, sending the first conversion result to the client.

In some possible embodiments, the preset conditions include: the first conversion result is the same as the second conversion result, and/or the third conversion result is a low-frequency conversion result relative to the first conversion result;

The second conversion result is obtained by converting the character string by using a word stock of the client; the third conversion result is other conversion results obtained by converting the character string by using the word stock of the server side besides the first conversion result.

In a second aspect, an embodiment of the present application further provides a method for providing input candidates, where the method is applied to a client, and includes:

receiving the combined content sent by the server side; the combined content is composed of a first conversion result and the following content of the input content, wherein the first conversion result is a conversion result of a character string input by a user on the client, and the input content at least comprises the first conversion result;

And determining the merged content as a server-side input candidate item.

In some possible embodiments, the method further comprises:

transmitting the input text before the character string input on the client to the server;

wherein the entered content further comprises a context entered on the client prior to the character string input.

In some possible embodiments, the method further comprises:

Receiving the first conversion result sent by the server side; the first conversion result is a conversion result obtained by converting the character string by using a word stock of the server side;

And if the first conversion result does not meet the preset condition, determining the first conversion result as the server-side input candidate item.

Correspondingly, the determining the merged content as the server-side input candidate comprises the following specific steps: and if the received first conversion result meets a preset condition, determining the combined content as the server-side input candidate item.

In a third aspect, an embodiment of the present application further provides an apparatus for providing input candidates, where the apparatus is applied to a server, and includes:

The acquisition module is used for acquiring a first conversion result of the character string input by the user on the client;

an analysis module for analyzing the following content of the inputted content according to the inputted content, wherein the inputted content at least comprises the first conversion result;

A composition module for composing a combined content with the context content with the first conversion result;

the sending module is used for sending the combined content to the client;

In some possible embodiments, the analysis module comprises:

an acquisition unit configured to acquire the inputted content as a current context;

a first determining unit, configured to determine a context entry of the current context;

A return unit, configured to, if the context probability of the current context and the context entry is greater than a probability threshold, re-use the content composed of the current context and the context entry as the current context, and return to execute the context entry for determining the current context;

a second determining unit configured to determine a portion of the current context other than the inputted content as the context content if a context probability of the current context and the context entry is not greater than a probability threshold;

In some possible embodiments, the method further comprises:

the conversion result sending module is used for sending the first conversion result to the client;

In some possible embodiments, the analyzing module is specifically configured to analyze the context of the input content according to the input content if the first conversion result meets a preset condition;

The conversion result sending module is specifically configured to send the first conversion result to the client if the first conversion result does not meet a preset condition.

In a fourth aspect, an embodiment of the present application further provides an apparatus for providing input candidates, where the apparatus is applied to a terminal, including:

the receiving module is used for receiving the combined content sent by the server side; the combined content is composed of a first conversion result and the following content of the input content, wherein the first conversion result is a conversion result of a character string input by a user on the client, and the input content at least comprises the first conversion result;

and the determining module is used for determining the combined content as a server-side input candidate.

In some possible embodiments, the method further comprises:

a sending module, configured to send, to the server, the input context on the client before the character string is input;

In some possible embodiments, the method further comprises:

The conversion result receiving module is used for receiving the first conversion result sent by the server side; the first conversion result is a conversion result obtained by converting the character string by using a word stock of the server side;

and the candidate item determining module is used for determining the first conversion result as the server-side input candidate item if the first conversion result does not meet the preset condition.

Correspondingly, the determining module is specifically configured to determine the combined content as the server-side input candidate item if the received first conversion result meets a preset condition.

In a fifth aspect, an embodiment of the present application further provides an apparatus for providing input candidates, including a memory, and one or more programs, where the one or more programs are stored in the memory, and configured to be executed by the one or more processors, where the one or more programs include a method for providing input candidates described in the first aspect, or a method for providing input candidates described in the second aspect.

In a sixth aspect, embodiments of the present application further provide a non-transitory computer-readable storage medium, which when executed by a processor of an electronic device, enables the electronic device to perform the method for providing input candidates described in the first aspect or the method for providing input candidates described in the second aspect.

Compared with the prior art, the embodiment of the invention has the following advantages:

In the embodiment of the invention, the server side can acquire a first conversion result obtained by the client side aiming at the character string input by the user, and analyze the context content of the input content according to the input content of the user, wherein the input content at least comprises the first conversion result; after the first conversion result and the following content are obtained, the first conversion result and the following content can be combined to obtain combined content composed of the first conversion result and the following content, and the combined content is sent to the client, wherein the combined content is used as a server side input candidate item on the client. When providing the input candidate items, the server side sends the combined content obtained based on the character strings input by the user to the client side, so that even if the conversion result obtained by the client side and the server side aiming at the character strings input by the user is the same, the server side provides the input candidate items comprising the conversion result and predicted context content for the user, namely the candidate items comprising the follow-up possible continuous input content of the user, thereby fully utilizing the resources of the server side, enabling the server side to provide the input candidate items which are different from the input candidate items of the client side for the user in the input process of the user, and enriching the input candidate items obtained by the user; moreover, based on the characteristics of larger word stock and stronger computing power at the server side, the hit rate of the input candidate provided by the server side for the expected input of the user is relatively high, so that the input cost of the next step of the user can be saved, and the input efficiency of the user is improved.

Drawings

In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings that are required to be used in the embodiments or the description of the prior art will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments described in the present invention, and other drawings may be obtained according to the drawings without inventive effort to those skilled in the art.

FIG. 1 is a schematic diagram of an exemplary application scenario in an embodiment of the present invention;

FIG. 2 is a flowchart of a method for providing input candidates according to an embodiment of the present invention;

FIG. 3 is a schematic diagram of distinguishing input candidates provided by a client and a server using different display areas;

FIG. 4 is a schematic diagram of a client displaying input candidates;

FIG. 5 is a schematic diagram of distinguishing input candidates provided by a client and a server using special markers;

FIG. 6 is a flowchart of another method for providing input candidates according to an embodiment of the present invention;

FIG. 7 is a flowchart of another method for providing input candidates according to an embodiment of the present invention;

FIG. 8 is a schematic diagram of an apparatus for providing input candidates according to an embodiment of the present invention;

FIG. 9 is a schematic diagram of another apparatus for providing input candidates according to an embodiment of the present invention;

FIG. 10 is a schematic diagram of an apparatus for providing input candidates according to an embodiment of the present invention;

fig. 11 is a schematic structural diagram of a server according to an embodiment of the present invention.

Detailed Description

The word stock at the server side can provide more words than the word stock at the client side, and the computing power of the server side is generally better than that of the client side, so the server side can provide the user with richer input candidates based on the character strings input by the user. However, the inventor found that in the existing input method system, the positioning of the server side is usually complementary to the client side, that is, if the client side is different from the preferred input candidate obtained by the server side based on the character string input by the user, the preferred input candidate provided by the server side is presented in a specific area on the input interface, however, if the preferred input candidate obtained by the client side and the preferred input candidate obtained by the server side based on the character string input by the user are the same, only the input candidate provided by the client side is typically presented on the input interface, which is equivalent to that the server side does not actually provide the input candidate for the user, thereby wasting resources of the server side, and the input candidate obtained by the user is not abundant enough, so that the user may need more input operations to achieve the expected input result.

In order to solve the above problems, in the embodiment of the present invention, the combined content including the conversion result and the association result provided by the server is displayed on the client, so that the server can provide the user with input candidates different from the client, so that the input candidates obtained by the user are richer, and the input operation of the user is simpler and more convenient. Specifically, the server side may obtain a first conversion result obtained by the client side for the character string input by the user, and analyze the context content of the input content according to the input content of the user, where the input content at least includes the first conversion result; after the first conversion result and the following content are obtained, the first conversion result and the following content can be combined to obtain combined content composed of the first conversion result and the following content, and the combined content is sent to the client, wherein the combined content is used as a server side input candidate item on the client. When providing the input candidate items, the server side sends the combined content obtained based on the character strings input by the user to the client side, so that even if the conversion result obtained by the client side and the server side aiming at the character strings input by the user is the same, the server side provides the input candidate items comprising the conversion result and predicted context content for the user, namely the input candidate items comprising the follow-up possible continuous input content of the user, thereby fully utilizing the resources of the server side, enabling the server side to provide the input candidate items which are different from the input candidate items of the client side for the user in the input process of the user, and enriching the input candidate items obtained by the user; moreover, based on the characteristics of larger word stock and stronger computing power at the server side, the hit rate of the input candidate provided by the server side for the expected input of the user is relatively high, so that the input cost of the next step of the user can be saved, and the input efficiency of the user is improved.

By way of example, the embodiments of the present invention may be applied to an exemplary application scenario as shown in fig. 1. In this scenario, the user 101 inputs a character string on the client 102, and the client may send an acquisition request of the input candidate item to the server 103, where the request may include the character string input by the user 101 on the client 102; the server 103 may parse the received request and obtain a first conversion result based on the character string included in the request, and then, the server 103 may analyze the context of the first conversion result according to the first conversion result, and form a combined content with the analyzed context and the first conversion result; after obtaining the combined content, the server 103 may send the combined content to the client 102, so that the client 102 may display the received combined content to the user 101 and mark as a server input candidate.

It should be noted that the above application scenario is only shown for the convenience of understanding the present invention, and embodiments of the present invention are not limited in this respect. Rather, embodiments of the invention may be applied to any scenario where applicable. For example, in other possible application scenarios, the request sent by the client 102 to the server 103 may not include a string input by the user 101 on the client 102, but may include a conversion result obtained by the client 102 based on the string, and then the server 103 may predict the following content directly based on the conversion result of the client 102 to obtain the combined content, without performing the conversion process or the like.

In order to make the present invention better understood by those skilled in the art, the following description will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings, and it is apparent that the described embodiments are only some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.

Referring to fig. 2, fig. 2 shows a flowchart of a method for providing input candidates in an embodiment of the present invention, where the method may be applied to a server, and the method may specifically include:

S201: and acquiring a first conversion result of the character string input by the user on the client.

In this embodiment, the server side is to provide the user with different input candidates based on the character string input by the user, and based on this, the server side may first obtain the conversion result of the character string input by the user on the client side.

It should be noted that, the first conversion result is a result obtained after complete conversion based on the character string input by the user, and may be not only a conversion result obtained by converting the character string by the server terminal based on the word stock of the server terminal, but also a conversion result obtained by converting the character string by the client terminal based on the local word stock of the client terminal. In an exemplary implementation of obtaining the first conversion result, the user inputs the character string on the client, the client may generate a request for obtaining the input candidate, where the request may include the character string input by the user, and then the client may send the request to the server; the server side can analyze the received request and convert the character string input by the analyzed user on the client side, so as to obtain a first conversion result. For example, the user inputs a "niyouaiqiyi" character string on the client, and the client may send the character string to the server along with the generated request, and the server converts the character string to obtain a first conversion result as "you have loving art".

Since the client may also convert the character string input by the user in the practical application, in addition to the conversion of the character string by the server to obtain the first conversion result in the above embodiment, in another exemplary implementation manner of obtaining the first conversion result, the server may also obtain the first conversion result obtained based on the conversion of the character string from the client. Specifically, after a user inputs a character string on a client, the client may convert the character string to obtain a first conversion result, then a request for obtaining an input candidate may be generated, the first conversion result obtained by conversion of the client is sent to a server along with the request, and the server may parse the received request to obtain the first conversion result. For example, a user may input a string "niyouaiqiyi" on the client, the client may convert the string to obtain a first conversion result "you have an loving art", and then the client may send the "you have an loving art" to the server along with the generated request for obtaining the input candidate, so that the server may parse the request to obtain the first conversion result "you have an loving art".

Further, whether the client sends the character string to the server or sends the conversion result obtained based on the character string to the server may be determined by the client according to the probability that the client corresponds the character string to the first conversion result. Specifically, after the client converts the character string input by the user, if the probability of correspondence between the character string and the conversion result obtained by conversion is greater than a preset value, which indicates that the conversion result is a term expected to be input by the user with higher probability, the client can take the conversion result as a first conversion result and send the first conversion result to the server; if the probability of correspondence between the character string and the conversion result is not greater than the preset value, which indicates that the conversion result is a vocabulary entry expected to be input by the user, the client may send the character string to the server, and the server converts the character string to obtain the first conversion result.

For example, assuming that a user inputs a character string "niyouaiqiyi" on a client, a possible conversion result obtained by converting the character string by the client may be "you have a loving art", and the like, if the client determines that the probability of the conversion result being "you have a loving art" is greater than 75% based on "niyouaiqiyi", the client considers that the content expected to be input by the user to input the character string is highly likely to be "you have a loving art", and may send "you have a loving art" to the server as a first conversion result; however, if the client determines that the conversion result is "your loving" based on "niyouaiqiyi", and determines that the conversion result is "your loving" based on "niyouaiqiyi" are both lower than 75%, it is considered that the content expected to be input by the user to input the character string is "your loving" and "your loving" are both lower, the client may send the character string "niyouaiqiyi" to the server, and the server performs conversion based on the character string, so as to obtain the first conversion result.

S202: and analyzing the following content of the input content according to the input content, wherein the input content at least comprises a first conversion result.

In this embodiment, after the server side obtains the first conversion result, the server side may predict the following content of the first conversion result. For example, if the first conversion result obtained by the server side is "the curiosity", the following content of "the curiosity" may be predicted to be "the member", "the account number password", etc.

In practical applications, when analyzing the context of the inputted content according to the inputted content, the inputted content may include not only the first conversion result but also the context that has been inputted before the character string is inputted on the client. In particular, the client may send the context that has been input on the client before the input of the input string to the server, so that the server may predict the context in combination with the content that has been input by the user on the screen and the obtained first conversion result. For example, before the user inputs the character string "aiqiyi", the user has already input the "you have" context, and when analyzing and predicting the content of the context, the server may analyze in combination with the "you have" context and the first conversion result "loving" corresponding to the character string "aiqiyi", that is, analyze the content of the context such as "member", "account password" and the like according to the "you have loving".

It should be noted that, in this embodiment, the content analyzed by the server may be composed of a plurality of entries. For example, when analyzing the existing input content "you have an loving" context, the resulting context may be "is a member? ". That is, the entered content and analyzed content below may be combined into a completed phrase.

As an exemplary implementation of analyzing the context, the server side may utilize probabilities to continuously predict the context vocabulary entries. Specifically, the server side may acquire the input content as a current context, determine a context term possibly corresponding to the current context, and if the context probability of the current context and the context term is greater than a probability threshold, take the content formed by the current context and the context term as a new current context, and continuously determine a new context term possibly corresponding to the new current context, where the context probability indicates the possibility that the current context and the context term are input into a context by a user; then, the server may determine whether the context probability between the new current context and the new context entry is greater than the probability threshold, and repeat the above process until the context probability between the new current context and the new context entry is not greater than the probability threshold, at which time, a portion of the new current context that belongs to the content other than the inputted content may be determined as the context content. Based on the above procedure, it is possible to determine the context content including a plurality of context entries using the context probability between the current context and the context entry.

For example, assuming that the server side takes the input content "your loving art" as the current context, it may determine that the corresponding context vocabulary entry is "member" based on the current context, then the server side may determine whether the context probability of the current context "your loving art" and the context vocabulary entry is greater than a preset probability threshold, if so, form the new current context "you have loving art" with "member", and continue to execute the step of determining the context vocabulary entry, and if it is determined that the context vocabulary entry corresponding to the new current context is "member", then it may continue to determine whether the context probability between "you have loving art member" and "member" is greater than the preset probability threshold, repeat the above process until the context probability between the new current vocabulary entry and the new context vocabulary entry is not greater than the probability threshold, and exit the above repeated process when the repeated process is executed multiple times, where the obtained new context has been obtained as "loving art" after the repeated process is repeatedly executed multiple times? "is the new current context part of the member outside of the entered content" you have loving "can be made? "determine to be the content of the following, the determined content of the following includes a plurality of terms," member "," is "and"? ".

In the above embodiment, the context is determined according to the binary relation between the current context and the context entry, and in other possible embodiments, the context may also be determined by adopting a multiple relation, and since the corresponding specific implementation means exist in the prior art for determining the context by adopting the multiple relation, the description is omitted herein.

S203: and combining the first conversion result with the analyzed content.

S204: and sending the combined content to the client, wherein the combined content is used as a server-side input candidate item on the client.

It will be appreciated that the analyzed context may be what the user desires to continue to input after inputting the first conversion result, and thus, after determining the context, the server may combine the first conversion result with the analyzed context and send the combined content to the client, so as to display on the client as an input candidate.

Therefore, if the input content expected by the user is the combined content, the user can directly click the input candidate item corresponding to the combined content to complete the input, so that after the user inputs the character string of part of the content, the user does not need to continuously input the character string, further the next input cost of the user is saved, and the user can conveniently input the character string. For example, as shown in fig. 3, the character string input by the user is "niyouaiqiyi", and the input candidate for the merged content to be displayed to the user on the client is "do you have an loved one? "is the user expecting to input" do you have an loved one? The character string 'niyouaiqiyi' can be input only in the process of 'without inputting the character strings corresponding to other contents'. For another example, as shown in fig. 4, the user has input "you have" on screen before entering the string "aiqiyi", and the input candidate that the consolidated content is displayed to the user on the client may be "is an alien member? ". Thus, the user is expecting to input "do you have an loved one? In the whole process of ' can firstly input the character ' you have ' on the screen, and then ' can obtain ' can be an lover? "so that the user can be saved for" is a member? "the input cost of the contents is convenient for the user to input.

Note that the client may display different regions on the input method interface when displaying the input candidate corresponding to the merged content. For example, in the example shown in fig. 3, the input candidate corresponding to the merged content "do you have an lover? "can be displayed in the display area 1, and input candidates obtained based on the local word stock of the client, such as" you have an loving skill ", and the like, can be displayed in the display area 2. The input candidates displayed in the display area 1 can be generally characterized as input candidates provided by the server side.

In addition to the above-mentioned distinction between input candidates provided by the client and the server using different display areas, distinction may also be performed by a special mark displayed on the input method interface. For example, in the example shown in fig. 5, the input candidate provided by the server side (i.e., the input candidate corresponding to the merged content) "do you have an lover? "can be displayed in the same display area as the input candidate" you have an loving art "provided by the client, and" do you have an loving art member? "can be identified with cloud labels, which characterizes the input candidates provided by the server side, while" you have loving "input candidates without cloud labels characterizes that they are provided by the client side. Of course, fig. 5 is merely illustrative and not limiting as to the implementation of a provider that uses special markers to distinguish input candidates. For example, other special marks may be employed, or the position of the special mark may be at any position near the input candidate, or the like.

In a further embodiment, the two embodiments may be combined to distinguish between input candidates provided by the client and the server. That is, while the input candidates provided by the client and the server are distinguished by using different display areas, the input candidates provided by the server may be identified by using a special mark displayed on the input method interface.

It can be understood that, in the process of obtaining the first conversion result, if a plurality of conversion results are obtained based on the character string input by the user, one conversion result can be determined from the plurality of conversion results as the first conversion result, and the input candidate provided by the server can be obtained by analysis based on the determined first conversion result. Of course, in practical application, it is also possible to set that only one input preference is displayed in the display area without considering the number of characters of the input candidate provided by the server side, and the present invention is not limited thereto.

As an example, the server side may determine the first conversion result according to the probability that the conversion result is input expected by the user, and in general, the greater the probability that the conversion result is input expected by the user, the greater the probability that the user desires to input the conversion result, so the conversion result with the maximum probability value may be taken as the first conversion result. In practical applications, the probability that the conversion result is expected to be input by the user may be represented by the word frequency of the input conversion result in the user history input behavior, and generally, the larger the word frequency is, the larger the probability value is, the smaller the word frequency is, and the smaller the probability value is. For example, if the character string input by the user is "anjian", the conversion result obtained based on the character string "anjian" may include "case", "key", "security check", "press" and the like, and if the word frequency of inputting each conversion result in the input behavior based on the history of the user is 580 times, 450 times, 120 times and 15 times in order, the probability that the content actually expected to be input when the user inputs the character string "anjian" is considered to be the "case" is the largest, and then the "case" may be used as the first conversion result.

Correspondingly, a plurality of input candidates provided by the server side can be presented in the display area. Specifically, if a plurality of conversion results are obtained based on the character string input by the user, the server may analyze, for each conversion result, an input candidate corresponding to the conversion result, so that a plurality of input candidates may be obtained based on the plurality of conversion results. In this way, the client can present a plurality of input candidates analyzed by the server in a display area on the input method display interface.

In this embodiment, the server may obtain a first conversion result obtained by the client for the character string input by the user, and analyze the context content of the input content according to the input content of the user, where the input content includes at least the first conversion result; after the first conversion result and the following content are obtained, the first conversion result and the following content can be combined to obtain combined content composed of the first conversion result and the following content, and the combined content is sent to the client, wherein the combined content is used as a server side input candidate item on the client. When providing the input candidate items, the server side sends the combined content obtained based on the character strings input by the user to the client side, so that even if the conversion result obtained by the client side and the server side aiming at the character strings input by the user is the same, the server side provides the input candidate items containing predicted context content for the user, namely the candidate items containing the follow-up possible continuous input content of the user, thereby fully utilizing the resources of the server side, enabling the server side to provide different input candidate items for the user than the client side in the input process of the user, and enriching the input candidate items obtained by the user; moreover, based on the characteristics of larger word stock and stronger computing power at the server side, the hit rate of the input candidate provided by the server side for the expected input of the user is relatively high, so that the input cost of the next step of the user can be saved, and the input efficiency of the user is improved.

In the above embodiment, the server side sends the merged content to the client side, and in practical application, since the word stock of the server side can provide more terms relative to the local word stock of the client side, when the first conversion result obtained by the server side is a result obtained by converting the character string based on the word stock of the server side, the first conversion result obtained by the server side may not be consistent with the conversion result of the character string by the client side, and based on this, in some possible embodiments, the server side may also send the first conversion result obtained by the server side to the client side. Next, a detailed description will be given with reference to fig. 5.

Referring to fig. 6, fig. 6 is a flowchart of a method for providing input candidates according to an embodiment of the present invention, where the method may specifically include:

S601: the server side converts the character strings input by the user on the client side to obtain a first conversion result.

In this embodiment, the first conversion result obtained by the server may be obtained by converting the character string input by the user based on the word stock of the server. Meanwhile, the client side can convert the character string input by the user based on the local word stock of the client side to obtain a second conversion result. Because the lexicon at the server side can provide more entries than the local lexicon at the client side, the first conversion result may not be the same as the second conversion result in some scenarios. It should be noted that the first conversion result and the second conversion result are both the results of complete conversion on the character string. For example, a user inputs a "niyouaiqiyi" character string on the client, a first conversion result obtained by converting the character string by the server may be "you have an loving art", a second conversion result obtained by converting the character string by the client may be "you have an loving art", and the first conversion result and the second conversion result are different.

Correspondingly, when the client requests the server to provide the input candidate, the request sent to the server contains the character string input by the user.

S602: the server side analyzes the following content of the inputted content according to the inputted content, wherein the inputted content at least comprises a first conversion result.

S603: the server side combines the content with the following content according to the first conversion result.

In this embodiment, the implementation processes of step S602 and step S603 are similar to the implementation processes of step S202 and step S203 in the previous embodiment, respectively, and may be described with reference to the relevant points in the previous embodiment, which is not described herein.

S604: the server side sends the combined content and the first conversion result to the client side.

Unlike the previous embodiment, since the first conversion result obtained by the server side based on the character string input by the user may be different from the second conversion result obtained by the client side, the server side may simultaneously transmit the combined content and the first conversion result to the client side.

S605: the client compares whether the received first conversion result is consistent with the second conversion result, wherein the second conversion result is obtained by converting the character string based on the word stock local to the client, if so, step S606 is executed, and if not, step S607 is executed.

S606: the client determines the first conversion result as a server-side input candidate.

It can be understood that if the client determines that the first conversion result is inconsistent with the second conversion result through comparison, the client may display the first conversion result provided by the server as an input candidate of the server to the user, so as to provide the conversion result of the server on the character string to the user.

S607: the client determines the merged content as server-side input candidates.

It can be understood that if the client determines that the first conversion result is consistent with the second conversion result through comparison, in order to provide richer input candidate items for the user, the client can display the combined content sent by the server as the input candidate item of the server to the user, so that the resources of the server can be fully utilized, more input candidate items are provided for the user, and the waste of the server resources is avoided.

In this embodiment, when the conversion results of the client and the server for the character strings input by the user are inconsistent based on different word libraries, the client may display the conversion results provided by the server on the input method interface, so that even if the conversion results obtained by the client and the server for the character strings input by the user are the same, the server provides the user with input candidates including the conversion results and predicted context, that is, candidates including possible continuous input of the user, and displays the candidates on the input method interface of the client, thereby fully utilizing the resources of the server, so that in the input process of the user, the server provides the user with different input candidates from the client, and enriches the input candidates obtained by the user; moreover, based on the characteristics of larger word stock and stronger computing power at the server side, the hit rate of the input candidate provided by the server side for the user to input is relatively higher, so that the input cost of the next step of the user can be saved.

In the above embodiment, the client determines the consistency of the first conversion result and the second conversion result, but when the first conversion result and the second conversion result are inconsistent, the client typically uses the first conversion result as a server to input candidate items and displays the candidate items on the input method interface, but for the combined content, the client may not display the candidate items on the input method interface. Therefore, in other possible embodiments, the server may determine the consistency of the first conversion result and the second conversion result, and when it is determined that the first conversion result is inconsistent with the second conversion result, the server may not need to analyze the merged content based on the input content, so that the computing resource of the server may be reduced. Specifically, referring to fig. 7, fig. 7 is a flowchart of another method for providing input candidates according to an embodiment of the present invention, where the method specifically may include:

S701: the server side obtains a second conversion result and a character string input by the user on the client side, wherein the second conversion result is obtained by converting the character string based on a word stock local to the client side.

In specific implementation, after a user inputs a character string on a client, the client can utilize a local word stock to convert the character string to obtain a second conversion result. Then, the client may send the second conversion result and the character string input by the user to the server along with the acquisition request of the input candidate generated on the client, so that the server may parse the second conversion result and the character string input by the user on the client from the acquisition request.

S702: the server side converts the character strings input by the user on the client side to obtain a first conversion result.

After the server side obtains the character string, the character string can be converted by using a word stock on the server side to obtain a second conversion result. Since the lexicon at the server side can provide more entries than the local lexicon at the client side, the first conversion result may be the same as the second conversion result or may be different from the first conversion result. It should be noted that the first conversion result and the second conversion result are both the results of complete conversion on the character string.

S703: the server compares whether the first conversion result and the second conversion result are consistent, if not, the step S704 is executed, and if so, the step S705 is executed.

S704: the server side sends a first conversion result to the client side, so that the client side takes the first conversion result as a server side input candidate.

It can be understood that, if the server determines that the first conversion result is inconsistent with the second conversion result through comparison, in view of that the client side generally displays the first conversion result as an input candidate provided by the server side on the input method interface, the server side may send the first conversion result to the client side and display the first conversion result on the input method interface of the client side, and may not analyze the combined content based on the first conversion result, so that the user may be provided with the input candidate of the server side and meanwhile, the computing resource of the server side may be saved.

S705: the server side analyzes the following content of the inputted content according to the inputted content, wherein the inputted content at least comprises a first conversion result.

S706: the server side combines the content with the following content according to the first conversion result.

S707: the server side sends the merged content to the client side so that the client side takes the merged content as a server side input candidate.

In this embodiment, the implementation process of step S705 to step S707 is similar to the implementation process of step S202 to step S204 in the above embodiment, and the description may be made with reference to the relevant points of the above embodiment, which is not repeated here.

In this embodiment, the server side can determine whether to analyze the merged content according to the consistency of the first conversion result and the second conversion result, so that when the first conversion result is inconsistent with the second conversion result, the server side does not need to analyze the merged content based on the first conversion result, thereby saving the computing resources of the server side while providing the input candidate of the server side for the user.

In practical application, in the conversion results obtained by converting the character string input by the user by using the word stock at the server side, if the word frequencies of the rest of conversion results except the first conversion result are lower than those of the first conversion result, the possibility that the first conversion result is the content expected to be input when the user inputs the character string is higher, and the possibility that the rest of conversion results are the content expected to be input by the user is lower. For convenience of description, the conversion results other than the first conversion result are described with a third conversion result, and accordingly, the third conversion result may include one or more conversion results. Based on this, in addition to the above embodiment, the server side may predict the following content of the inputted content when determining that the first conversion result is the same as the second conversion result, or the server side may analyze and predict the following content according to the inputted content when determining that the third conversion result is a conversion result of a low frequency with respect to the first conversion result.

That is, in some possible embodiments, when determining that the server side analyzes the context of the input content according to the input content, the first conversion result needs to meet a preset condition, and the preset condition may be either the first conversion result and the second conversion result, or the third conversion result is a low-frequency conversion result relative to the first conversion result, or a combination of the first conversion result and the second conversion result, that is, the third conversion result is a low-frequency conversion result relative to the first conversion result while the first conversion result is the same as the third conversion result.

In some embodiments for determining whether the third conversion result is a low-frequency conversion result, after obtaining a plurality of conversion results based on the character string input by the user, the server may determine whether the word frequency of each conversion result exceeds a preset value, take the conversion result with the word frequency lower than the preset value as the third conversion result, and correspondingly, take the conversion result with the word frequency not lower than the preset value as the first conversion result. Of course, the third conversion result may also be determined based on the word frequency difference between the two conversion results. Specifically, in other embodiments for determining whether the third conversion result is a low-frequency conversion result, the server may calculate a word frequency difference value of the two conversion results, and determine whether the difference value is greater than a preset value, if the word frequency difference value is greater than the preset value, then the conversion result with a smaller word frequency may be determined as the third conversion result, and correspondingly, the conversion result with a larger word frequency may be determined as the first conversion result.

Correspondingly, the server side can also determine whether to send the first conversion result to the client side based on whether the first conversion result meets a preset condition. Specifically, if the server determines that the first conversion result meets the preset condition, that is, the first conversion result is the same as the second conversion result, and/or the third conversion result is a low-frequency conversion result relative to the first conversion result, the server may send the combined content to the client, and then the client may display the combined content as an input candidate of the server on the input method interface, so as to provide more input candidates for the user; if the first conversion result does not meet the preset condition, that is, the first conversion result is not the same as the second conversion result, and/or the third conversion result is not a low-frequency conversion result relative to the first conversion result, the server side may send the first conversion result to the client side, and further the client side may display the first conversion result as a server side candidate on the input method display interface, so as to provide more input candidates for the user.

In addition, the embodiment of the invention also provides a device for providing input candidate items. Referring to fig. 8, fig. 8 is a schematic structural diagram of an apparatus for providing input candidates according to an embodiment of the present invention, and the apparatus 800 may specifically include:

An obtaining module 801, configured to obtain a first conversion result of a character string input by a user on a client;

An analysis module 802 for analyzing a content following the inputted content according to the inputted content, wherein the inputted content at least comprises the first conversion result;

a composition module 803 for composing a combined content with the context content with the first conversion result;

a sending module 804, configured to send the merged content to the client;

In some possible implementations, the analysis module 802 includes:

In some possible embodiments, the apparatus 800 further comprises:

In some possible embodiments, the analyzing module 802 is specifically configured to analyze the context of the input content according to the input content if the first conversion result meets a preset condition;

In this embodiment, when providing the input candidate, the server sends the merged content obtained based on the character string input by the user to the client, so that even if the conversion result obtained by the client and the server for the character string input by the user is the same, the server provides the user with the input candidate including the predicted context content, that is, the candidate including the content that the user may continue to input subsequently, thereby fully utilizing the resources of the server, enabling the server to provide the user with different input candidate from the client in the input process of the user, and enriching the input candidate obtained by the user; moreover, based on the characteristics of larger word stock and stronger computing power at the server side, the hit rate of the input candidate provided by the server side for the expected input of the user is relatively high, so that the input cost of the next step of the user can be saved, and the input efficiency of the user is improved.

In addition, the embodiment of the application also provides a device for providing input candidate items, which is applied to the terminal. Referring to fig. 9, fig. 9 is a schematic structural diagram of an apparatus for providing input candidates according to an embodiment of the present application, and the apparatus 900 may specifically include:

a receiving module 901, configured to receive the combined content sent by the server side; the combined content is composed of a first conversion result and the following content of the input content, wherein the first conversion result is a conversion result of a character string input by a user on the client, and the input content at least comprises the first conversion result;

a determining module 902, configured to determine the combined content as a server-side input candidate.

In some possible embodiments, the apparatus 900 further comprises:

Correspondingly, the determining module 902 is specifically configured to determine the combined content as the server-side input candidate if the received first conversion result meets a preset condition.

Referring to fig. 10, the apparatus 1000 may include one or more of the following components: a processing component 1002, a memory 1004, a power component 1006, a multimedia component 1008, an audio component 1010, an input/output (I/O) interface 1012, a sensor component 1014, and a communication component 1016.

The processing component 1002 generally controls overall operation of the apparatus 1000, such as operations associated with display, telephone calls, data communications, camera operations, and recording operations. The processing component 1002 can include one or more processors 1020 to execute instructions to perform all or part of the steps of the methods described above. Further, the processing component 1002 can include one or more modules that facilitate interaction between the processing component 1002 and other components. For example, the processing component 1002 may include a multimedia module to facilitate interaction between the multimedia component 1008 and the processing component 1002.

The memory 1004 is configured to store various types of data to support operations at the device 1000. Examples of such data include instructions for any application or method operating on the device 1000, contact data, phonebook data, messages, pictures, videos, and the like. The memory 1004 may be implemented by any type or combination of volatile or nonvolatile memory devices such as Static Random Access Memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic or optical disk.

The power supply component 1006 provides power to the various components of the device 1000. The power supply component 10010 can include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power for the device 1000.

The multimedia component 1008 includes a screen between the device 1000 and the user that provides an output interface. In some embodiments, the screen may include a Liquid Crystal Display (LCD) and a Touch Panel (TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive input signals from a user. The touch panel includes one or more touch sensors to sense touches, swipes, and gestures on the touch panel. The touch sensor may sense not only the boundary of a touch or slide action, but also the duration and pressure associated with the touch or slide operation. In some embodiments, the multimedia assembly 1008 includes a front-facing camera and/or a rear-facing camera. The front camera and/or the rear camera may receive external multimedia data when the device 1000 is in an operational mode, such as a photographing mode or a video mode. Each front camera and rear camera may be a fixed optical lens system or have focal length and optical zoom capabilities.

The audio component 1010 is configured to output and/or input audio signals. For example, the audio component 1010 includes a Microphone (MIC) configured to receive external audio signals when the device 1000 is in an operational mode, such as a call mode, a recording mode, and a speech recognition mode. The received audio signals may be further stored in memory 1004 or transmitted via communication component 1016. In some embodiments, the audio component 1010 further comprises a speaker for outputting audio signals.

The I/O interface 1012 provides an interface between the processing assembly 1002 and peripheral interface modules, which may be a keyboard, click wheel, buttons, and the like. These buttons may include, but are not limited to: homepage button, volume button, start button, and lock button.

The sensor assembly 1014 includes one or more sensors for providing status assessment of various aspects of the device 1000. For example, the sensor assembly 1014 may detect the on/off state of the device 1000, the relative positioning of the components, such as the display and keypad of the apparatus 1000, the sensor assembly 1014 may also detect a change in position of the apparatus 1000 or a component of the apparatus 1000, the presence or absence of user contact with the apparatus 1000, the orientation or acceleration/deceleration of the apparatus 1000, and a change in temperature of the apparatus 1000. The sensor assembly 1014 may include a proximity sensor configured to detect the presence of nearby objects in the absence of any physical contact. The sensor assembly 1014 may also include a light sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, the sensor assembly 1014 can also include an acceleration sensor, a gyroscopic sensor, a magnetic sensor, a pressure sensor, or a temperature sensor.

The communication component 1016 is configured to facilitate communication between the apparatus 1000 and other devices, either wired or wireless. The device 1000 may access a wireless network based on a communication standard, such as WiFi,2G or 3G, or a combination thereof. In one exemplary embodiment, the communication part 1016 receives a broadcast signal or broadcast-related information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, the communication component 1016 further includes a Near Field Communication (NFC) module to facilitate short range communications. For example, the NFC module may be implemented based on Radio Frequency Identification (RFID) technology, infrared data association (IrDA) technology, ultra Wideband (UWB) technology, bluetooth (BT) technology, and other technologies.

In an exemplary embodiment, the apparatus 1000 may be implemented by one or more Application Specific Integrated Circuits (ASICs), digital Signal Processors (DSPs), digital Signal Processing Devices (DSPDs), programmable Logic Devices (PLDs), field Programmable Gate Arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic elements for executing the methods described above.

Specifically, an embodiment of the present invention provides an apparatus for providing input candidates, which may be embodied as an apparatus 1000, including a memory 1004, and one or more programs, where the one or more programs are stored in the memory 1004 and configured to be executed by one or more processors 1020, the one or more programs include instructions for:

Sending the combined content to the client;

In some possible implementations, the processor 1020 is specifically configured to execute the one or more programs including instructions for:

Acquiring the input content as a current context;

determining a context entry for the current context;

In some possible implementations, the processor 1020 is also configured to execute the one or more programs including instructions for:

sending the first conversion result to the client;

In some possible implementations, the processor 1020 is specifically configured to execute the one or more programs including instructions for: if the first conversion result meets a preset condition, analyzing the context content of the input content according to the input content; and if the first conversion result does not meet the preset condition, sending the first conversion result to the client.

Or an embodiment of the present invention provides an apparatus for providing input candidates, which may be embodied as a device 1000, including a memory 1004, and one or more programs, wherein the one or more programs are stored in the memory 1004 and configured to be executed by the one or more processors 1020, the one or more programs include instructions for:

And determining the merged content as a server-side input candidate item.

Accordingly, in some possible implementations, the processor 1020 is specifically configured to execute the one or more programs including instructions for:

and if the received first conversion result meets a preset condition, determining the combined content as the server-side input candidate item.

Embodiments of the present invention also provide a non-transitory computer-readable storage medium including instructions, such as memory 1004 including instructions, that are executable by processor 1020 of apparatus 1000 to perform the above-described method. For example, the non-transitory computer readable storage medium may be ROM, random Access Memory (RAM), CD-ROM, magnetic tape, floppy disk, optical data storage device, etc.

A non-transitory computer readable storage medium, which when executed by a processor of an electronic device, causes the electronic device to perform a method of providing input candidates, the method comprising:

Sending the combined content to the client;

Or the method comprises the following steps:

And determining the merged content as a server-side input candidate item.

Fig. 11 is a schematic structural diagram of a server according to an embodiment of the present invention. The server 1100 may vary considerably in configuration or performance and may include one or more central processing units (central processing units, CPUs) 1122 (e.g., one or more processors) and memory 1132, one or more storage mediums 1130 (e.g., one or more mass storage devices) that store applications 1142 or data 1144. Wherein the memory 1132 and the storage medium 1130 may be transitory or persistent. The program stored on the storage medium 1130 may include one or more modules (not shown), each of which may include a series of instruction operations on a server. Still further, the central processor 1122 may be provided in communication with a storage medium 1130, executing a series of instruction operations in the storage medium 1130 on the server 1100.

The server 1100 may also include one or more power supplies 1126, one or more wired or wireless network interfaces 1150, one or more input/output interfaces 1158, one or more keyboards 1156, and/or one or more operating systems 1141, such as Windows Server, mac OS XTM, unixTM, linuxTM, freeBSDTM, and the like.

Other embodiments of the invention will be apparent to those skilled in the art from consideration of the specification and practice of the invention disclosed herein. This invention is intended to cover any variations, uses, or adaptations of the invention following, in general, the principles of the invention and including such departures from the present disclosure as come within known or customary practice within the art to which the invention pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the invention being indicated by the following claims.

It is to be understood that the invention is not limited to the precise arrangements and instrumentalities shown in the drawings, which have been described above, and that various modifications and changes may be effected without departing from the scope thereof. The scope of the invention is limited only by the appended claims

The foregoing description of the preferred embodiments of the invention is not intended to limit the invention to the precise form disclosed, and any such modifications, equivalents, and alternatives falling within the spirit and scope of the invention are intended to be included within the scope of the invention.

Claims

1. A method for providing input candidates, which is applied to a server, comprising:

acquiring a first conversion result of a character string input by a user on a client, wherein the first conversion result is a conversion result obtained by converting the character string by using a word stock of the server;

Analyzing the context of the input content according to the input content when the first conversion result meets the preset condition, wherein the input content at least comprises the first conversion result, and the preset condition comprises the following steps: the first conversion result is the same as the second conversion result, and/or a third conversion result is a low-frequency conversion result relative to the first conversion result, the second conversion result is a conversion result obtained by converting the character string by using a word stock of the client, and the third conversion result is other conversion results obtained by converting the character string by using the word stock of the server except the first conversion result;

Sending the combined content to the client;

wherein the merged content is provided on the client as server side input candidates to provide different input candidates than the client.

2. The method of claim 1, wherein the entered content further comprises a context entered on the client prior to the character string input.

3. The method of claim 1, wherein the analyzing the context of the entered content based on the entered content comprises:

Acquiring the input content as a current context;

determining a context entry for the current context;

4. The method as recited in claim 1, further comprising:

sending the first conversion result to the client;

5. The method according to claim 4, wherein the sending the first conversion result to the client is specifically: and if the first conversion result does not meet the preset condition, sending the first conversion result to the client.

6. A method for providing input candidates, characterized by being applied to a client, comprising:

Receiving the combined content sent by the server side; the combined content is composed of a first conversion result and a following content of an inputted content, the first conversion result is a conversion result of a character string inputted by a user on a client, the first conversion result is a conversion result obtained by converting the character string by using a word stock of the server, the inputted content at least comprises the first conversion result, the following content is obtained according to analysis of the inputted content when the first conversion result meets a preset condition, and the preset condition comprises: the first conversion result is the same as the second conversion result, and/or a third conversion result is a low-frequency conversion result relative to the first conversion result, the second conversion result is a conversion result obtained by converting the character string by using a word stock of the client, and the third conversion result is other conversion results obtained by converting the character string by using the word stock of the server except the first conversion result;

the merged content is determined as server-side input candidates to provide input candidates different from the client.

7. The method as recited in claim 6, further comprising:

8. The method as recited in claim 6, further comprising:

receiving the first conversion result sent by the server side;

if the first conversion result does not meet the preset condition, determining the first conversion result as the server-side input candidate item;

9. An apparatus for providing input candidates, wherein the apparatus is applied to a server side, and comprises:

The acquisition module is used for acquiring a first conversion result of a character string input by a user on a client, wherein the first conversion result is a conversion result obtained by converting the character string by utilizing a word stock of the server;

The analysis module is configured to analyze, according to the inputted content, the content below the inputted content when the first conversion result meets a preset condition, where the inputted content includes at least the first conversion result, and the preset condition includes: the first conversion result is the same as the second conversion result, and/or a third conversion result is a low-frequency conversion result relative to the first conversion result, the second conversion result is a conversion result obtained by converting the character string by using a word stock of the client, and the third conversion result is other conversion results obtained by converting the character string by using the word stock of the server except the first conversion result;

the sending module is used for sending the combined content to the client;

10. The apparatus of claim 9, wherein the entered content further comprises a context entered on the client prior to the character string input.

11. The apparatus of claim 9, wherein the analysis module comprises:

12. The apparatus as recited in claim 9, further comprising:

13. The apparatus of claim 12, wherein the conversion result sending module is specifically configured to send the first conversion result to the client if the first conversion result does not meet a preset condition.

14. An apparatus for providing input candidates, the apparatus being applied to a terminal, comprising:

The receiving module is used for receiving the combined content sent by the server side; the combined content is composed of a first conversion result and a following content of an inputted content, the first conversion result is a conversion result of a character string inputted by a user on a client, the first conversion result is a conversion result obtained by converting the character string by using a word stock of the server, the inputted content at least comprises the first conversion result, the following content is obtained according to analysis of the inputted content when the first conversion result meets a preset condition, and the preset condition comprises: the first conversion result is the same as the second conversion result, and/or a third conversion result is a low-frequency conversion result relative to the first conversion result, the second conversion result is a conversion result obtained by converting the character string by using a word stock of the client, and the third conversion result is other conversion results obtained by converting the character string by using the word stock of the server except the first conversion result;

And the determining module is used for determining the combined content as a server-side input candidate to provide an input candidate different from the client.

15. The apparatus as recited in claim 14, further comprising:

16. The apparatus as recited in claim 14, further comprising:

the conversion result receiving module is used for receiving the first conversion result sent by the server side;

The candidate item determining module is used for determining the first conversion result as the server-side input candidate item if the first conversion result does not meet a preset condition;

17. An apparatus for providing input candidates, comprising a memory, and one or more programs, wherein the one or more programs are stored in the memory, and wherein execution of the one or more programs by one or more processors comprises execution of a method for providing input candidates according to any of the preceding claims 1 to 5, or execution of a method for providing input candidates according to any of the preceding claims 6 to 8.

18. A non-transitory computer readable storage medium, which when executed by a processor of an electronic device, causes the electronic device to perform the method of providing input candidates according to any of the preceding claims 1 to 5 or to perform the method of providing input candidates according to any of the preceding claims 6 to 8.